Nom du GPU | Ellesmere | GP104 |
---|---|---|
GPU variant | Ellesmere XT | N17E-Q1-A1 |
Architecture | GCN 4.0 | Pascal |
Fonderie | GlobalFoundries | TSMC |
Taille du processus | 14 nm | 16 nm |
Transistors | 5,700 million | 7,200 million |
Taille des matrices | 232 mm² | 314 mm² |
Date de publication | Mar 1st, 2017 | Jan 11th, 2017 |
---|---|---|
Génération | Radeon Pro Mobile (WX x100) | Quadro Mobile (Px000) |
Production | Active | End-of-life |
Bus interface | PCIe 3.0 x16 | MXM-B (3.0) |
Base clock | 1188 MHz | 1088 MHz |
---|---|---|
Boost clock | 1243 MHz | 1215 MHz |
Mémoire clock | 1250 MHz 5 Gbps effective | 1753 MHz 7 Gbps effective |
Taille de la mémoire | 8 GB | 6 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR5 |
Bus mémoire | 256 bit | 192 bit |
Bande passante | 160.0 GB/s | 168.3 GB/s |
Shading units | 2304 | 1280 |
---|---|---|
TMUs | 144 | 80 |
ROPs | 32 | 48 |
Compute units | 36 | — |
Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
Cache L2 | 2 MB | 1536 KB |
Comptage SM | — | 10 |
Taux de pixel | 39.78 GPixel/s | 58.32 GPixel/s |
---|---|---|
Taux de texture | 179.0 GTexel/s | 97.20 GTexel/s |
FP32 (float) performance | 5.728 TFLOPS | 3.110 TFLOPS |
FP64 (double) performance | 358.0 GFLOPS (1:16) | 97.20 GFLOPS (1:32) |
FP16 (half) performance | — | 48.60 GFLOPS (1:64) |
Taille Slot | MXM Module | MXM Module |
---|---|---|
Longueur | 25 mm 1 inches | — |
TDP | 130 W | 75 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | None |
DirectX | 12 (12_0) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.4 | 6.4 |
CUDA | — | 6.1 |